{"id":"https://openalex.org/W4416286512","doi":"https://doi.org/10.1109/tvt.2025.3633791","title":"Joint Service Placement and Resource Allocation for Long-Term DNN Inference Accuracy in Dynamic MEC Networks","display_name":"Joint Service Placement and Resource Allocation for Long-Term DNN Inference Accuracy in Dynamic MEC Networks","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416286512","doi":"https://doi.org/10.1109/tvt.2025.3633791"},"language":null,"primary_location":{"id":"doi:10.1109/tvt.2025.3633791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3633791","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046383678","display_name":"Z W Zhang","orcid":"https://orcid.org/0009-0001-2541-8636"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihan Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2541-8636","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102913097","display_name":"Tiankui Zhang","orcid":"https://orcid.org/0000-0002-0694-5844"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiankui Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0694-5844","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057582611","display_name":"Tianyi Shi","orcid":"https://orcid.org/0000-0003-0070-6719"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Shi","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0070-6719","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052878834","display_name":"Yapeng Wang","orcid":"https://orcid.org/0000-0003-1849-972X"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yapeng Wang","raw_affiliation_strings":["School of Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35678116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"6","first_page":"12007","last_page":"12012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.4916999936103821,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.4916999936103821,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2159000039100647,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12079","display_name":"IoT Networks and Protocols","score":0.05460000038146973,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7876999974250793},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.5299000144004822},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4851999878883362},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4830000102519989},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/channel-allocation-schemes","display_name":"Channel allocation schemes","score":0.4406999945640564},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.43950000405311584},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.42910000681877136},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7876999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807000279426575},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.5299000144004822},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C114237682","wikidata":"https://www.wikidata.org/wiki/Q5072483","display_name":"Channel allocation schemes","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.4212999939918518},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C101403955","wikidata":"https://www.wikidata.org/wiki/Q6707083","display_name":"Lyapunov optimization","level":5,"score":0.3465000092983246},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2025.3633791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3633791","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1924309553","display_name":null,"funder_award_id":"62371068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"By":[0,66],"leveraging":[1],"deep":[2],"neural":[3],"networks":[4,9],"(DNNs),":[5],"mobile":[6],"edge":[7],"computing":[8,14],"can":[10,35],"integrate":[11],"advanced":[12],"intelligent":[13],"capabilities.":[15],"Due":[16],"to":[17,49,80,110],"temporally":[18],"dynamic":[19],"changes":[20],"in":[21,115,154],"wireless":[22,63],"channel":[23],"and":[24,62,73,157],"service":[25,58,132,143],"requesting":[26],"distribution,":[27],"the":[28,43,51,68,82,86,113,117,126,149],"long-term":[29,52,91],"inference":[30,53,74,155],"accuracy":[31,54,156],"of":[32,99],"DNN":[33],"services":[34],"be":[36],"severely":[37],"affected":[38],"over":[39],"time.":[40],"To":[41],"address":[42],"above":[44],"challenge,":[45],"this":[46],"correspondence":[47],"aims":[48],"maximize":[50],"by":[55],"jointly":[56],"optimizing":[57],"placement,":[59],"bandwidth":[60,123],"allocation,":[61,124],"device":[64],"association.":[65],"modeling":[67],"relationship":[69],"between":[70],"data":[71],"size":[72],"accuracy,":[75],"we":[76],"employ":[77],"regression":[78],"techniques":[79],"derive":[81],"fitting":[83],"curve":[84],"for":[85,122,131,142],"deployed":[87],"services.":[88],"A":[89],"two-timescale":[90],"optimization":[92,108],"problem":[93],"is":[94,120,129,139],"transformed":[95],"into":[96],"a":[97,135],"series":[98],"subproblems":[100],"using":[101],"Lyapunov":[102],"analysis.":[103],"We":[104],"propose":[105],"an":[106],"alternating":[107],"algorithm":[109],"tackle":[111],"with":[112],"subproblems,":[114],"which":[116],"convex-concave":[118],"procedure":[119],"utilized":[121],"while":[125],"branch-and-bound":[127],"method":[128,138],"employed":[130],"placement.":[133,144],"Moreover,":[134],"low-complexity":[136],"penalty-based":[137],"further":[140],"developed":[141],"Simulation":[145],"results":[146],"show":[147],"that":[148],"proposed":[150],"methods":[151],"outperform":[152],"baselines":[153],"system":[158],"fairness.":[159]},"counts_by_year":[],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-11-17T00:00:00"}